© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13979
    Prev
    Next
    INDEX
    Explanations

    phrases that are used when discussing expectations in interpersonal relationships

    oai_token-act-pair · gemini-2.0-flash

    very

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.63
    Enllaces
    -0.62
    antMatchers
    -0.53
    getDoctrine
    -0.52
    ברס
    -0.51
     متعلقه
    -0.48
    id
    -0.48
    ỵ
    -0.47
    ínsula
    -0.47
     migli
    -0.47
    POSITIVE LOGITS
     very
    2.13
    very
    1.85
    Very
    1.77
     Very
    1.70
     VERY
    1.60
    VERY
    1.56
     très
    1.40
     sehr
    1.33
     muy
    1.27
    sehr
    1.23
    Activations Density 2.314%

    No Known Activations